# min(DALL·E)

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/kuprel/min-dalle/blob/main/min_dalle.ipynb)  
[![Replicate](https://replicate.com/kuprel/min-dalle/badge)](https://replicate.com/kuprel/min-dalle)

This is a minimal implementation of Boris Dayma's [DALL·E Mini](https://github.com/borisdayma/dalle-mini) in PyTorch.  It has been stripped to the bare essentials necessary for doing inference.  The only third party dependencies are numpy and torch.

It currently takes **7.4 seconds** to generate an image with DALL·E Mega with PyTorch on a standard GPU runtime in Colab

The flax model, and the code for coverting it to torch, have been moved [here](https://github.com/kuprel/min-dalle-flax).

### Install

```bash
$ pip install min-dalle
```  

### Usage

Use the python script `image_from_text.py` to generate images from the command line.

```bash
$ python image_from_text.py --text='artificial intelligence' --seed=7
```
![Artificial Intelligence](examples/artificial_intelligence.png)

```bash
$ python image_from_text.py --text='court sketch of godzilla on trial' --mega
```
![Godzilla Trial](examples/godzilla_on_trial.png)

To load a model once and generate multiple times, first initialize `MinDalleTorch`

```python
from min_dalle import MinDalleTorch

model = MinDalleTorch(
    is_mega=True, 
    is_reusable=True,
    models_root='./pretrained'
)
```

The required models will be downloaded to `models_root` if they are not already there.  After the model has loaded, call `generate_image` with some text and a seed as many times as you want.

```python
image = model.generate_image("a comfy chair that looks like an avocado")
display(image)
```
![Avocado Armchair](examples/avocado_armchair.png)

```python
image = model.generate_image(
    "trail cam footage of gollum eating watermelon", 
    seed=1
)
display(image)
```
![Gollum Trailcam](examples/gollum_trailcam.png)